Claims › Agent model › C006

C006

In their own words · Andreas 2022 · §1 Introduction, (C1) · contested

…In particular, I claim:

“In the course of performing next-word prediction in context, current LMs sometimes infer approximate, partial representations of the beliefs, desires and intentions possessed by the agent that produced the context, and other agents mentioned within it.”

(C2) Once these representations are inferred, they are causally linked to LM prediction, and thus bear the same relation to generated text that an intentional agent’s state bears to its communciative actions.…

Predicting the next word can require the model to build a partial picture of what the writer believed and wanted. The claim is about representations inside the system, not about the system being someone.

The five layers, for this claim

1 Free tag Andreas a name finds, it does not vouch
2 Topic Meaning closed list
3 Theme What a machine cannot be said to do derived from the topic
4 Concept Agent model a note and links
5 Geometry 1.5 0.75 proceedings or preprint + 1 × 0.25 × 1.5 contested

Relations

Notation

Claim typeWhat kind of statement it is, so that the right test can be applied. Proposed until checked by hand.
D1.14 · metaphysical-ontological
FunctionWhat a claim does for the programme: a conceptual tool, a working method, corrective evidence, a technical reference.
conceptual tool
StanceHow the programme holds the claim: assumed, used, or contested.
contested
Used in
/lab/2026-07-21-what-counts-as-a-verdict/
Cite this
claudiocammarano.com/en/claims/c006/